All tasks
Task·audio
Text-to-Speech AI Models & Workflows
Give your workflow a voice. Pick a text-to-speech model, drop it into a NodeTool graph, and turn scripts into narration and voiceover — with your own keys.
Models for text to speech
ElevenLabs v3
audioElevenLabs
Expressive, multi-lingual voices with cloning.
OpenAI TTS
audioOpenAI
Clean, reliable narration voices.
Kokoro
audioLocal (MLX)
Open-weight TTS that runs on Apple Silicon.
Frequently asked questions
What is text-to-speech?
It converts written text into spoken audio using an AI voice — useful for narration, voiceover, and accessibility.
Can I clone or customize a voice?
With providers like ElevenLabs, yes. Swap the TTS node's model and voice settings to change how it sounds.
Does it run offline?
Local models such as Kokoro run entirely in NodeTool Studio on your own machine — no network needed.
Do text to speech on your own machine
Free, open source, and yours to run. Download Studio, pick a model, and wire it into a workflow with your own keys.